Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds

By G. Sithole, George Vosselman. 2004

1,099 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/f4dd8e8861729325d21bace23271761f04e44b41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Geology

Citations in the corpus

3D Terrestrial LiDAR data classification of complex natural scenes using a multi-scale dimensionality criterion: applications in geomorphology (2011, background): “5D airborne lidar or mostly 2D point clouds ([13, 17, 28, 42]).”
Advances in fusion of optical imagery and LiDAR point cloud applied to photogrammetry and remote sensing (2017, methodology): “So far, many filtering methods have been proposed, and most of them are reviewed in (Sithole and Vosselman 2004, Meng et al. 2010).”
Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure (2015, methodology): “Accurate co-registration of canopy surface models and DTMs from different data sources represents a major challenge to accurately estimating canopy structure [35,60,62,63] and remains a significant challenge for using Ecosynth UAV-SFM remote sensing to estimate canopy height [14,22].”
Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests (2011, background): “Many authors have shown the potential of multi-echo lidar data for urban area analysis and building extraction based on filtering and segmentation processes (Matikainen et al., 2003; Sithole and Vosselman, 2004; Rottensteiner et al., 2007; Matei et al., 2008).”
NON-ASSOCIATIVE MARKOV NETWORKS FOR 3D POINT CLOUD CLASSIFICATION (2010, methodology): “The common thing in these approaches is that filters always operate only on a local neighbourhood of points (Sithole and Vosselman, 2004).”
Automatic Construction of Building Footprints From Airborne LIDAR Data (2006, methodology): “Numerous algorithms have been developed to identify ground measurements from LIDAR data [12].”
An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation (2016, methodology): “This method was first tested by datasets that were provided by the International Society for Photogrammetry and Remote Sensing (ISPRS) Working Group III/3 to quantitatively test the performance of different filters and identify directions for future research [30].”
Airborne LiDAR for DEM generation: some critical issues (2008, background): “Slope-based filters work well in fairly flat terrain, but become more difficult as the slope of the terrain increases (Sithole and Vosselman, 2004), especially in a steep forested landscape.”
Analyzing High Resolution Topography for Advancing the Understanding of Mass and Energy Transfer Through Landscapes: A Review (2015, background): “A second issue is that many algorithms for bare earth detection have been developed for 2.5D geometry typical of ALS surveys (e.g., Sithole and Vosselman, 2004; Tinkham et al., 2011) and can fail when applied in steep landscapes, or cannot be applied on vertical surfaces documented by TLS (e.g.,…”
High spatial resolution three-dimensional mapping of vegetation spectral dynamics using computer vision (2013, methodology): “As in LIDAR postprocessing, these “ noise ” points were removed from point clouds after georeferencing using statistical outlier ﬁ ltering (Sithole & Vosselman, 2004).”
Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extraction * (2007, background): “There is, however, no unified filtering algorithm, which is robust to all different landforms (Sithole and Vosselman, 2004).”
Estimation of stand variables in Pinus radiata D. Don plantations using different LiDAR pulse densities (2012, methodology): “Accordingly, it is possible to generate a Digital Terrain Model (DTM) by filtering LiDAR data (for algorithm comparison, see Sithole and Vosselman, 2004) and interpolating the points classified as ground and a Digital Surface Model (DSM) by interpolating the first return”
An improved simple morphological filter for the terrain classification of airborne LIDAR data (2013, methodology): “There have been many attempts to categorize ground filtering algorithms based on their methodology (e.g., Liu, 2008; Sithole and Vosselman, 2004).”